Code release for the paper CMT: Co-training Mean-Teacher for Unsupervised Domain Adaptation on 3D Object Detection, ACM MM 2024. The codebase is still under updating.
CMT is an unsupervised domain adaption method on 3D object detection.
We provide pretrained models here for these task in models.
| Car@R40 | |
|---|---|
| SECOND-IoU | 72.1 |
| PV-RCNN | 74.5 |
| Car@R40 | |
|---|---|
| SECOND-IoU | 68.1 |
| PVRCNN | 75.5 |
| Car@R40 | |
|---|---|
| SECOND-IoU | 24.3 |
| PVRCNN | 26.4 |
Please refer to INSTALL.md for the installation of OpenPCDet.
Please refer to GETTING_STARTED.md to learn more usage about this project.
If you find this project useful in your research, please consider cite our paper.
Our code is heavily based on OpenPCDet, ST3D, DTS. Thanks for their awesome codebase.